Deep Learning & Neural Networks Interview Questions Hindi mein

Deep Learning & Neural Networks कोर्स के 25 सवाल, हर सवाल के सही जवाब और explanation के साथ। जवाब देखने से पहले ख़ुद सोचें।

Neural Network Foundations

1. What is a key advantage of deep learning over classic ML?

  1. It is always cheaper
  2. It never needs data
  3. It learns useful features directly from raw data
  4. It works best on tiny tables
जवाब देखें

जवाब: It learns useful features directly from raw data

Representation learning is the core idea.

पाठ: What Deep Learning Is

2. Why are activation functions needed?

  1. They make the network non-linear; without them stacked layers equal one linear layer
  2. They store the training data
  3. They speed up disk access
  4. They replace the weights
जवाब देखें

जवाब: They make the network non-linear; without them stacked layers equal one linear layer

Non-linearity gives networks their power.

पाठ: Neurons and Activation Functions

3. Why can't a single linear layer solve XOR?

  1. XOR needs images
  2. XOR has too much data
  3. Linear layers have no weights
  4. XOR's classes cannot be separated by a straight line
जवाब देखें

जवाब: XOR's classes cannot be separated by a straight line

Hidden non-linear layers bend the boundary.

पाठ: Why Hidden Layers Matter: The XOR Problem

How Networks Learn

4. Which loss is standard for multi-class classification?

  1. Mean squared error on class ids
  2. Cross-entropy on the logits
  3. Accuracy
  4. Number of parameters
जवाब देखें

जवाब: Cross-entropy on the logits

Cross-entropy penalises low probability on the true class.

पाठ: Loss Functions

5. What does backpropagation compute?

  1. The final accuracy
  2. The gradient of the loss with respect to every weight, via the chain rule
  3. The dataset size
  4. The best learning rate
जवाब देखें

जवाब: The gradient of the loss with respect to every weight, via the chain rule

Gradients tell each weight which way to move.

पाठ: Gradient Descent and Backpropagation

6. Why call optimizer.zero_grad() each step?

  1. It loads new data
  2. It saves the model
  3. It sets the learning rate
  4. PyTorch accumulates gradients by default
जवाब देखें

जवाब: PyTorch accumulates gradients by default

Clear old gradients before computing new ones.

पाठ: Automatic Differentiation in PyTorch

7. What does momentum add to SGD?

  1. A running direction that smooths noisy gradients
  2. A larger dataset
  3. Random weight resets
  4. A second loss function
जवाब देखें

जवाब: A running direction that smooths noisy gradients

Momentum accelerates along consistent directions.

पाठ: Optimisers: SGD, Momentum and Adam

The PyTorch Workflow

8. What shape convention do PyTorch image layers expect?

  1. (channels, batch)
  2. (height, width) only
  3. (batch, channels, height, width)
  4. (pixels, labels)
जवाब देखें

जवाब: (batch, channels, height, width)

NCHW is the default layout.

पाठ: Tensors and Shapes

9. What is the correct order inside a training step?

  1. backward, zero_grad, step, forward
  2. step, backward, forward, loss
  3. zero_grad, forward, loss, backward, step
  4. forward, step, zero_grad, backward
जवाब देखें

जवाब: zero_grad, forward, loss, backward, step

Clear, compute, differentiate, update.

पाठ: Modules and the Training Loop

10. What is an epoch?

  1. One full pass over the training data
  2. One weight update
  3. One layer
  4. One GPU
जवाब देखें

जवाब: One full pass over the training data

Many mini-batch steps make up an epoch.

पाठ: Mini-Batches, Epochs and Devices

Making Training Work

11. How do residual connections help deep networks train?

  1. They freeze the first layer
  2. They remove all activations
  3. They reduce the dataset
  4. They give gradients a direct path around each block
जवाब देखें

जवाब: They give gradients a direct path around each block

Skip connections keep gradients flowing.

पाठ: Vanishing Gradients, Normalisation and Residual Connections

12. When is dropout active?

  1. Only during evaluation
  2. During training only; it is disabled in eval mode
  3. Never
  4. Only when saving the model
जवाब देखें

जवाब: During training only; it is disabled in eval mode

model.eval() turns dropout off.

पाठ: Regularisation: Dropout, Weight Decay and Augmentation

13. What does early stopping keep?

  1. The last checkpoint always
  2. The checkpoint with the best validation score
  3. The first checkpoint
  4. Only the optimiser state
जवाब देखें

जवाब: The checkpoint with the best validation score

Stop when validation stops improving and keep the best.

पाठ: Learning-Rate Schedules and Early Stopping

Convolutional Neural Networks

14. What does a convolutional filter produce?

  1. A new dataset
  2. A single class label
  3. A loss value
  4. A feature map showing where its pattern appears
जवाब देखें

जवाब: A feature map showing where its pattern appears

Filters respond to local patterns.

पाठ: The Convolution Operation

15. What does max pooling do?

  1. Keeps the strongest value in each window, shrinking the feature map
  2. Adds more pixels
  3. Normalises the labels
  4. Computes the loss
जवाब देखें

जवाब: Keeps the strongest value in each window, shrinking the feature map

Pooling downsamples and adds shift tolerance.

पाठ: Building a Small CNN

16. Why does a convolution layer have few parameters?

  1. It only processes one pixel
  2. It has no weights
  3. The same small filter is shared across all image positions
  4. It stores the dataset
जवाब देखें

जवाब: The same small filter is shared across all image positions

Weight sharing is the key.

पाठ: Why Convolutions Are Efficient

Sequences, Embeddings and Attention

17. What is an embedding layer?

  1. A data loader
  2. A loss function
  3. A learnable lookup table from ids to dense vectors
  4. A type of pooling
जवाब देखें

जवाब: A learnable lookup table from ids to dense vectors

Embeddings turn discrete ids into learnable vectors.

पाठ: Embeddings: Tokens as Vectors

18. Why did transformers replace RNNs for most language tasks?

  1. They process tokens in parallel and handle long-range context better
  2. RNNs cannot learn at all
  3. Transformers need no data
  4. RNNs only work on images
जवाब देखें

जवाब: They process tokens in parallel and handle long-range context better

Parallel attention scales better.

पाठ: Recurrent Networks and Their Limits

19. What do attention weights in each row sum to?

  1. The model size
  2. 0
  3. The sequence length
  4. 1, because of the softmax
जवाब देखें

जवाब: 1, because of the softmax

They form a weighted average over values.

पाठ: Self-Attention

Transformers, Transfer Learning and Generative Models

20. Why do transformers need positional information?

  1. Attention only works on images
  2. Self-attention by itself does not know token order
  3. To reduce parameters
  4. Because embeddings are random
जवाब देखें

जवाब: Self-attention by itself does not know token order

Positions are added to the token vectors.

पाठ: The Transformer Block

21. Why is transfer learning usually preferred over training from scratch?

  1. It never needs a validation set
  2. It needs much less data and compute because the model already has useful features
  3. It makes models smaller automatically
  4. Pretrained models cannot be changed
जवाब देखें

जवाब: It needs much less data and compute because the model already has useful features

Start from what the model already knows.

पाठ: Transfer Learning and Fine-Tuning

22. How do autoregressive language models generate text?

  1. By sorting the vocabulary
  2. By denoising an image
  3. By clustering documents
  4. By predicting the next token repeatedly
जवाब देखें

जवाब: By predicting the next token repeatedly

Next-token prediction, one step at a time.

पाठ: Generative Models at a Glance

Debugging, Deploying and a Checklist

23. What does failing to overfit a single small batch suggest?

  1. A bug in the model, loss or training step
  2. The dataset is too large
  3. The model is perfect
  4. You need more epochs on all data
जवाब देखें

जवाब: A bug in the model, loss or training step

A working setup can memorise a few examples.

पाठ: Debugging Neural Networks

24. Why call model.eval() before inference?

  1. It saves the model to disk
  2. It trains the model faster
  3. It disables dropout and uses stored batch-norm statistics for consistent outputs
  4. It increases the learning rate
जवाब देखें

जवाब: It disables dropout and uses stored batch-norm statistics for consistent outputs

Training-mode behaviour makes predictions noisy.

पाठ: Saving, Loading and Serving Models

25. Which item belongs on a deep learning checklist?

  1. Run inference in training mode
  2. Skip validation curves
  3. Verify the model can overfit a single batch
  4. Tune on the test set
जवाब देखें

जवाब: Verify the model can overfit a single batch

Sanity checks catch bugs early.

पाठ: A Deep Learning Project Checklist

← कोर्स पर वापस जाएँ